Data Mining Practical Machine Learning Tools and Techniques

Matrix Factorization Techniques for Recommender Systems

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

In this work, we model abstractive text summarization using Attentional EncoderDecoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora. We propose several novel models that address critical problems in summarization that are not adequately modeled by the basic architecture, such as modeling key-words, capturing the hierarchy of sentence-toword structure, and emitting words that are rare or unseen at training time. Our work shows that many of our proposed models contribute to further improvement in performance. We also propose a new dataset consisting of multi-sentence summaries, and establish performance benchmarks for further research.

/pdf/abstractive-text-summarization-using-sequence-to-sequence-3velxrqd2y.pdf

Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond

Getting to YES. Negotiating Agreement Without Giving In

We show that it is possible to reliably discriminate whether a syntactic construction is meant literally or metaphorically using lexical semantic features of the words that participate in the construction. Our model is constructed using English resources, and we obtain state-of-the-art performance relative to previous work in this language. Using a model transfer approach by pivoting through a bilingual dictionary, we show our model can identify metaphoric expressions in other languages. We provide results on three new test sets in Spanish, Farsi, and Russian. The results support the hypothesis that metaphors are conceptual, rather than lexical, in nature.

/pdf/metaphor-detection-with-cross-lingual-model-transfer-201rdqd1ha.pdf

Metaphor Detection with Cross-Lingual Model Transfer

A medicine cabinet or similar device that assists users in selecting and taking medication. A radio frequency receiver is configured to read information included on radio frequency sensitive labels that are attached to items containing medication in the medicine cabinet. A computer in the medicine cabinet is operatively connected to the radio frequency receiver and also to a wide area network, such as the Internet. The medicine cabinet has a display device that is operatively coupled with the computer and, in the form of a touch screen flat panel, the display device functions to interface the user and the medicine cabinet. The computer is configured to transmit information to the Internet and receives information from websites or additional computers that are coupled to the Internet. Information regarding medications and users as well as vital signs records of the users are stored either in the memory of the medicine cabinet or at a remote location via the connection to the Internet.

Online medicine cabinet

Ubiquitous computing will change the way we live with technology. As Mark Weiser stated: “The most profound technologies are those that disappear. They weave themselves into the fabric of everyday life until they are indistinguishable from it” [3]. We don’t think of pencils or hinges or faucets as technology. They are just simply features of the world we take for granted and shape the way we act in the world. With ubiquitous computing, using information technology will progressively feel more like using these everyday objects than using personal computers.

The future of business services in the age of ubiquitous computing

In the emerging field of micro-blogging and social communication services, users post millions of short messages every day. Keeping track of all the messages posted by your friends and the conversation as a whole can become tedious or even impossible. In this paper, we presented a study on automatically clustering and classifying Twitter messages, also known as “tweets”, into different categories, inspired by the approaches taken by news aggregating services like Google News. Our results suggest that the clusters produced by traditional unsupervised methods can often be incoherent from a topical perspective, but utilizing a supervised methodology that utilize the hash-tags as indicators of topics produce surprisingly good results. We also offer a discussion on temporal effects of our methodology and training set size considerations. Lastly, we describe a simple method of finding the most representative tweet in a cluster, and provide an analysis of the results.

/pdf/topical-clustering-of-tweets-39uhd3h43u.pdf

Topical Clustering of Tweets

We present the CSF - Common Semantic Features method for metaphor detection. This method has two distinguishing characteristics: it is cross-lingual and it does not rely on the availability of extensive manually-compiled lexical resources in target languages other than English. A metaphor detecting classifier is trained on English samples and then applied to the target language. The method includes procedures for obtaining semantic features from sentences in the target language. Our experiments with Russian and English sentences show comparable results, supporting our hypothesis that a CSF-based classifier can be applied across languages. We obtain state-ofthe-art performance in both languages.

Anatole Gershman

Papers

Metaphor Detection with Cross-Lingual Model Transfer

Online medicine cabinet

The future of business services in the age of ubiquitous computing

Topical Clustering of Tweets

Cross-Lingual Metaphor Detection Using Common Semantic Features